faiss-haystack 1.0.0__tar.gz → 2.0.0__tar.gz

{faiss_haystack-1.0.0 → faiss_haystack-2.0.0}/PKG-INFO

@@ -1,10 +1,11 @@
 Metadata-Version: 2.4
 Name: faiss-haystack
-Version: 1.0.0
+Version: 2.0.0
+Summary: An integration of FAISS (library for efficient similarity search of dense vectors) with Haystack
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/faiss#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/faiss
-Author-email: Deepset <info@deepset.ai>
+Author-email: deepset GmbH <info@deepset.ai>
 License-Expression: Apache-2.0
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
@@ -12,28 +13,24 @@ Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.10
 Requires-Dist: faiss-cpu>=1.8.0
-Requires-Dist: haystack-ai>=2.24.0
+Requires-Dist: haystack-ai>=2.26.1
 Requires-Dist: numpy<2,>=1.22; python_version < '3.13'
 Description-Content-Type: text/markdown
 
 # faiss-haystack
 
-This package provides a [FAISS](https://github.com/facebookresearch/faiss) document store for [Haystack](https://github.com/deepset-ai/haystack).
+[![PyPI - Version](https://img.shields.io/pypi/v/faiss-haystack.svg)](https://pypi.org/project/faiss-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/faiss-haystack.svg)](https://pypi.org/project/faiss-haystack)
 
-## Installation
+- [Integration page](https://haystack.deepset.ai/integrations/faiss-documentstore)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/faiss/CHANGELOG.md)
 
-```bash
-pip install faiss-haystack
-```
+---
 
-## Usage
-
-```python
-from haystack_integrations.document_stores.faiss import FAISSDocumentStore
-
-document_store = FAISSDocumentStore(index_path="my_index")
-```
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

faiss_haystack-2.0.0/README.md

@@ -0,0 +1,11 @@
+# faiss-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/faiss-haystack.svg)](https://pypi.org/project/faiss-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/faiss-haystack.svg)](https://pypi.org/project/faiss-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/faiss-documentstore)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/faiss/CHANGELOG.md)
+
+---
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

{faiss_haystack-1.0.0 → faiss_haystack-2.0.0}/pyproject.toml

@@ -5,12 +5,12 @@ build-backend = "hatchling.build"
 [project]
 name = "faiss-haystack"
 dynamic = ["version"]
-description = ''
+description = 'An integration of FAISS (library for efficient similarity search of dense vectors) with Haystack'
 readme = "README.md"
 requires-python = ">=3.10"
 license = "Apache-2.0"
 keywords = []
-authors = [{ name = "Deepset", email = "info@deepset.ai" }]
+authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
 classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
@@ -18,11 +18,13 @@ classifiers = [
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3.14",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
 dependencies = [
-  "haystack-ai>=2.24.0",
+  "haystack-ai>=2.26.1",
   "faiss-cpu>=1.8.0",
   "numpy>=1.22,<2; python_version < '3.13'",
 ]
@@ -48,7 +50,7 @@ installer = "uv"
 dependencies = ["haystack-pydoc-tools", "ruff"]
 
 [tool.hatch.envs.default.scripts]
-docs = ["pydoc-markdown pydoc/config_docusaurus.yml"]
+docs = ["haystack-pydoc pydoc/config_docusaurus.yml"]
 fmt = "ruff check --fix {args}; ruff format {args}"
 fmt-check = "ruff check {args} && ruff format --check {args}"
 
@@ -59,6 +61,7 @@ dependencies = [
     "pytest-rerunfailures",
     "mypy",
     "pandas",
+    "pip",    # needed for mypy to install type stubs
 ]
 
 [tool.hatch.envs.test.scripts]
@@ -75,8 +78,12 @@ non_interactive = true
 check_untyped_defs = true
 disallow_incomplete_defs = true
 
-[tool.hatch.metadata]
-allow-direct-references = true
+[[tool.mypy.overrides]]
+module = [
+  # faiss does not provide types
+  "faiss.*",
+]
+ignore_missing_imports = true
 
 [tool.ruff]
 line-length = 120
@@ -84,9 +91,17 @@ line-length = 120
 [tool.ruff.lint]
 select = [
   "A",
+  "ANN",
   "ARG",
   "B",
   "C",
+  "D102",   # Missing docstring in public method
+  "D103",   # Missing docstring in public function
+  "D205",   # 1 blank line required between summary line and description
+  "D209",   # Closing triple quotes go to new line
+  "D213",   # summary lines must be positioned on the second physical line of the docstring
+  "D417",   # Missing argument descriptions in the docstring
+  "D419",   # Docstring is empty
   "DTZ",
   "E",
   "EM",
@@ -128,6 +143,8 @@ ignore = [
   "ARG002",
   # Allow assertions
   "S101",
+  # Allow `Any` - used legitimately for dynamic types and SDK boundaries
+  "ANN401",
 ]
 exclude = ["example"]
 
@@ -139,7 +156,7 @@ ban-relative-imports = "parents"
 
 [tool.ruff.lint.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
-"tests/**/*" = ["PLR2004", "S101", "TID252"]
+"tests/**/*" = ["D", "PLR2004", "S101", "TID252", "ANN"]
 "example/**/*" = ["T201"]
 
 [tool.coverage.run]
@@ -156,4 +173,5 @@ exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 
 [tool.pytest.ini_options]
 minversion = "6.0"
+addopts = "--strict-markers"
 markers = ["integration: integration tests"]

{faiss_haystack-1.0.0 → faiss_haystack-2.0.0}/src/haystack_integrations/components/retrievers/faiss/embedding_retriever.py

@@ -59,8 +59,10 @@ class FAISSEmbeddingRetriever:
         filters: dict[str, Any] | None = None,
         top_k: int = 10,
         filter_policy: str | FilterPolicy = FilterPolicy.REPLACE,
-    ):
+    ) -> None:
         """
+        Initialize FAISSEmbeddingRetriever.
+
         :param document_store: An instance of `FAISSDocumentStore`.
         :param filters: Filters applied to the retrieved Documents at initialisation time. At runtime, these are merged
             with any runtime filters according to the `filter_policy`.

{faiss_haystack-1.0.0 → faiss_haystack-2.0.0}/src/haystack_integrations/document_stores/faiss/document_store.py

@@ -9,7 +9,6 @@ from dataclasses import replace
 from pathlib import Path
 from typing import Any
 
-import faiss  # type: ignore[import-untyped]
 import numpy as np
 from haystack import default_from_dict, default_to_dict
 from haystack.dataclasses import Document
@@ -17,6 +16,8 @@ from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumen
 from haystack.document_stores.types import DuplicatePolicy
 from haystack.errors import FilterError
 
+import faiss
+
 logger = logging.getLogger(__name__)
 
 
@@ -33,7 +34,7 @@ class FAISSDocumentStore:
         index_path: str | None = None,
         index_string: str = "Flat",
         embedding_dim: int = 768,
-    ):
+    ) -> None:
         """
         Initializes the FAISSDocumentStore.
 
@@ -60,7 +61,7 @@ class FAISSDocumentStore:
         else:
             self._create_new_index()
 
-    def _create_new_index(self):
+    def _create_new_index(self) -> None:
         """Creates a new FAISS index."""
         try:
             # We use IndexIDMap to support add_with_ids
@@ -488,18 +489,18 @@ class FAISSDocumentStore:
                 values.add(val)
         return list(values)
 
-    def count_unique_metadata_by_filter(self, filters: dict[str, Any], fields: list[str]) -> dict[str, int]:
+    def count_unique_metadata_by_filter(self, filters: dict[str, Any], metadata_fields: list[str]) -> dict[str, int]:
         """
         Returns a count of unique values for multiple metadata fields, optionally scoped by a filter.
 
         :param filters: A dictionary of filters to apply.
-        :param fields: A list of metadata field names to count unique values for.
+        :param metadata_fields: A list of metadata field names to count unique values for.
         :returns: A dictionary mapping each field name to the count of its unique values.
         """
         filtered_docs = self.filter_documents(filters)
         counts = {}
 
-        for field in fields:
+        for field in metadata_fields:
             unique_vals = set()
             for doc in filtered_docs:
                 val = FAISSDocumentStore._get_doc_value(doc, field)

{faiss_haystack-1.0.0 → faiss_haystack-2.0.0}/tests/test_document_store.py

@@ -6,11 +6,16 @@ import pytest
 from haystack.dataclasses import Document
 from haystack.errors import FilterError
 from haystack.testing.document_store import (
+    CountDocumentsByFilterTest,
     CountDocumentsTest,
+    CountUniqueMetadataByFilterTest,
     DeleteAllTest,
     DeleteByFilterTest,
     DeleteDocumentsTest,
     FilterDocumentsTest,
+    GetMetadataFieldMinMaxTest,
+    GetMetadataFieldsInfoTest,
+    GetMetadataFieldUniqueValuesTest,
     UpdateByFilterTest,
 )
 
@@ -24,20 +29,23 @@ class TestFAISSDocumentStore(
     UpdateByFilterTest,
     DeleteAllTest,
     DeleteByFilterTest,
+    CountDocumentsByFilterTest,
+    CountUniqueMetadataByFilterTest,
+    GetMetadataFieldsInfoTest,
+    GetMetadataFieldMinMaxTest,
+    GetMetadataFieldUniqueValuesTest,
 ):
     @pytest.fixture
     def document_store(self, tmp_path):
         return FAISSDocumentStore(index_path=str(tmp_path / "test_index"))
 
     def test_write_documents(self, document_store):
-
         doc = Document(content="test")
         document_store.write_documents([doc])
         assert document_store.count_documents() == 1
         assert document_store.filter_documents()[0].id == doc.id
 
     def test_persistence(self, tmp_path):
-
         path = tmp_path / "persistent_index"
         ds = FAISSDocumentStore(index_path=str(path), embedding_dim=3)
 
@@ -73,7 +81,6 @@ class TestFAISSDocumentStore(
             ds.load(path)
 
     def test_search_with_and_without_filters(self, document_store):
-
         # Setup documents with missing/varied embeddings to test edge cases
         doc1 = Document(content="test1", embedding=[0.1, 0.2, 0.3], meta={"category": "A"})
         doc2 = Document(content="test2", embedding=[0.4, 0.5, 0.6], meta={"category": "B"})
@@ -97,7 +104,6 @@ class TestFAISSDocumentStore(
 
     def test_to_dict_from_dict(self):
         ds = FAISSDocumentStore(index_path="test_index", index_string="Flat", embedding_dim=128)
-
         data = ds.to_dict()
         assert data["type"] == "haystack_integrations.document_stores.faiss.document_store.FAISSDocumentStore"
         assert data["init_parameters"]["index_path"] == "test_index"
@@ -109,50 +115,7 @@ class TestFAISSDocumentStore(
         assert ds_loaded.index_string == "Flat"
         assert ds_loaded.embedding_dim == 128
 
-    def test_count_documents_by_filter(self, document_store):
-
-        docs = [
-            Document(content="test1", meta={"category": "A"}),
-            Document(content="test2", meta={"category": "B"}),
-            Document(content="test3", meta={"category": "A"}),
-        ]
-        document_store.write_documents(docs)
-
-        count = document_store.count_documents_by_filter(
-            filters={"field": "meta.category", "operator": "==", "value": "A"}
-        )
-        assert count == 2
-
-    def test_get_metadata_fields_info(self, document_store):
-
-        docs = [Document(content="test1", meta={"category": "A", "count": 1, "is_active": True})]
-        document_store.write_documents(docs)
-
-        info = document_store.get_metadata_fields_info()
-        assert "category" in info
-        assert info["category"]["type"] == "keyword"
-        assert "count" in info
-        assert info["count"]["type"] == "long"
-        assert "is_active" in info
-        assert info["is_active"]["type"] == "boolean"
-
-    def test_count_unique_metadata_by_filter(self, document_store):
-
-        docs = [
-            Document(content="test1", meta={"category": "A", "status": "active"}),
-            Document(content="test2", meta={"category": "B", "status": "inactive"}),
-            Document(content="test3", meta={"category": "A", "status": "active"}),
-        ]
-        document_store.write_documents(docs)
-
-        counts = document_store.count_unique_metadata_by_filter(
-            filters={"field": "meta.category", "operator": "==", "value": "A"}, fields=["meta.status"]
-        )
-        assert "meta.status" in counts
-        assert counts["meta.status"] == 1  # Only "active" status for category A
-
     def test_not_filter_with_empty_conditions_raises_filter_error(self, document_store):
         document_store.write_documents([Document(content="test", meta={"category": "A"})])
-
         with pytest.raises(FilterError, match="NOT operator expects at least one condition"):
             document_store.filter_documents(filters={"operator": "NOT", "conditions": []})

faiss_haystack-1.0.0/README.md

@@ -1,17 +0,0 @@
-# faiss-haystack
-
-This package provides a [FAISS](https://github.com/facebookresearch/faiss) document store for [Haystack](https://github.com/deepset-ai/haystack).
-
-## Installation
-
-```bash
-pip install faiss-haystack
-```
-
-## Usage
-
-```python
-from haystack_integrations.document_stores.faiss import FAISSDocumentStore
-
-document_store = FAISSDocumentStore(index_path="my_index")
-```

faiss_haystack-1.0.0/src/haystack_integrations/components/__init__.py

@@ -1,3 +0,0 @@
-# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
-#
-# SPDX-License-Identifier: Apache-2.0

faiss_haystack-1.0.0/src/haystack_integrations/components/retrievers/__init__.py

@@ -1,3 +0,0 @@
-# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
-#
-# SPDX-License-Identifier: Apache-2.0